David Dalcu
@ddalcu
I build things, local LLM engines & UI’s. Created for Desktop and MLX Chat for iOS. (Zig based engine)
Joined June 2010
583 Following 878 Followers
Qwen 3.8 Flash-Next is alive on MLX-Serve, under 128gb, working on performance next. MTP gets ~20tok a second, no MTP gets 30+ ... investigating why..
